Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dates in "Month Year" format

    oai_token-act-pair · gpt-3.5-turbo

    the word "a" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Edit
    -0.92
    coins
    -0.80
    Enjoy
    -0.80
    <?
    -0.79
    lets
    -0.78
    plates
    -0.76
    Contents
    -0.75
    lly
    -0.73
    apps
    -0.73
    lest
    -0.72
    POSITIVE LOGITS
     couple
    1.06
     successful
    1.05
     concerted
    1.04
     lengthy
    1.02
     slight
    1.02
     brief
    0.98
     few
    0.97
     protracted
    0.97
     prolonged
    0.94
     slew
    0.93
    Act Density 0.148%

    No Known Activations